Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/sekera-radim/impriWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/sekera-radim/impri/impri)<a href="https://agentmods.dev/mcp/sekera-radim/impri/impri"><img src="https://agentmods.dev/badge/mcp/sekera-radim/impri/impri/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/sekera-radim/impri/impri"><img src="https://agentmods.dev/badge/mcp/sekera-radim/impri/impri.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
impri scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"impri": {
"command": "npx",
"args": [
"-y",
"@impri/mcp"
],
"env": {
"IMPRI_API_KEY": "",
"IMPRI_BASE_URL": ""
}
}
}What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 13 lines scan A ea808b8ca129
impri is an MCP server published in the GitHub repository sekera-radim/impri (6 stars, last pushed 4d ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other mcp servers, from other repositories
agentgate
Human-in-the-loop approval gateway for AI agents over MCP: request, decide, approve. Runs locally from the @agentkitai/agentgate-mcp npm package.
llm-safe-sql
Let an LLM propose UPDATE/DELETE, then actually run it, measure the real before/after diff, and always roll back — so the human approves measured facts, not the model's claim. Runs locally from the @hyuga/llm-safe-sql npm package.
gatehouse
Permission tiers, approval gates, and audit logging for MCP servers — the server is the gatekeeper. Runs locally from the mcp-gatehouse Python package.
signet-gateway
MCP server "signet-gateway" as configured in bee-san/Signet. Runs locally from the signet-gateway Python package.
humane-proxy
Lightweight, plug-and-play AI safety middleware that protects humans. Runs locally from the humane-proxy Python package. Needs 2 environment variables to run.
semantix-ai
A Semantic Type System for AI outputs — validate intent, not just shape. Runs locally from the semantix-ai Python package.